本研究探討在生成式人工智慧 (Generative AI) 普及的環境下，高中學生面對數位資訊之媒體識讀表現、查證意願與互動行為。學習者面對高認知負荷的資訊判讀任務時，可能依賴外部工具、直接接受現成資訊，呈現低投入或與後設認知懶惰 (Metacognitive Laziness)、認知卸載 (Cognitive Offloading) 相關的行為特徵。為回應此教育困境，本研究建置結合人工智慧偵探情境與數位鷹架的 AI 輔助資訊引導雛型系統，作為高中媒體識讀教學與資訊判讀練習的輔助工具。 本系統以鷹架理論 (Scaffolding Theory) 為基礎，透過媒體案件、熱區採證、分級提示與結案反思，引導學生觀察訊息、拆解線索、自主思考、主動求證與反思判斷。系統不直接揭示答案，而是依學生停留時間與錯誤點擊開放提示，學生主動點擊後，再由 AI 模組提供啟發式引導。另建構五階段思維層次分析架構 (被動接收、訊息拆解、自主思考、主動求證、初步內化跡象)，作為系統任務、歷程編碼與互動分析的操作性架構。 本研究採單一組別前後測設計，進行短期介入，透過媒體識讀主觀態度量表、客觀能力測驗、互動日誌與典型個案資料進行評估。結果顯示，學生的媒體識讀主觀態度總分於介入後顯著提升；然而，客觀能力前後測未達顯著差異，顯示本研究尚未觀察到短期介入對客觀判讀能力或知識遷移的明顯影響。分析發現，部分學生呈現低投入或可能與認知卸載相關的特徵，如過快作答、反思不足或查證不充分；亦有學生展現訊息拆解、主動求證與較完整推理等高階行為。本研究系統與五階段架構可作為觀察高中學生數位資訊判讀歷程及設計媒體識讀教材的參考。惟結果限於短期介入的特定系統情境，不宜推論學生已形成穩定媒體識讀素養或認知卸載行為的長期改變。;This study examined senior high school students’ media-literacy performance， willingness to verify information， and interaction behaviors when encountering digital information in an environment where generative artificial intelligence (AI) has become widespread. When facing information-verification tasks with high cognitive demands， learners may rely on external tools or directly accept readily available information， displaying low engagement or behavioral characteristics associated with metacognitive laziness and cognitive offloading. To address this educational challenge， an AI-assisted information-guiding prototype system integrating an AI-detective scenario with digital scaffolding was developed to support senior high school media-literacy instruction and information-verification practice. Grounded in scaffolding theory， the system incorporated media cases， hotspot-based evidence collection， graduated prompts， and case-report reflection. These functions guided students to observe messages， deconstruct clues， think independently， actively verify information， and reflect on their judgments. Rather than directly revealing the answers， the system made prompts available according to students’ dwell time and erroneous clicks. After students actively selected the prompt function， the AI module provided heuristic guidance. In addition， a five-level framework for analyzing students’ thinking processes—comprising Passive Reception， Message Deconstruction， Independent Thinking， Active Verification， and Preliminary Signs of Internalization—was developed as an operational framework for system-task design， process coding， and interaction analysis. A one-group pretest–posttest design was adopted for a short-term intervention. The evaluation used a media-literacy attitude scale， an objective media-literacy assessment， interaction logs， and typical-case data. The results showed a significant improvement in students’ overall media-literacy attitude scores after the intervention. However， no significant pretest–posttest difference was found in objective performance， suggesting that the study did not observe clear short-term improvement in students’ information-evaluation ability or knowledge transfer. The analysis further showed that some students displayed low engagement or behavioral characteristics potentially related to cognitive offloading， such as responding too quickly， providing insufficient reflection， or conducting insufficient verification. Other students demonstrated higher-level behaviors， including message deconstruction， active verification， and more complete reasoning. Overall， the prototype system and the five-level framework may serve as an initial reference for examining senior high school students’ digital information-verification processes and designing media-literacy materials. However， the findings should be interpreted only within the specific system context of the short-term intervention and should not be taken as evidence that students had developed stable media-literacy competencies or experienced long-term changes in cognitive offloading behaviors.
